Celebrate IEEE Day with CIS Distingushed Lecturer Professor Hussein Abbass

Register

Call for Associate Editors for the IEEE Transactions on Artificial Intelligence

Deadline for applying: 3 December 2022

Each year, the IEEE Transactions on Artificial Intelligence (IEEE TAI) invites new Associate Editors (AEs) to join its editorial board due to completion of the term of some existing AEs, retention of some AEs, or an increased load on existing AEs in some areas of AI.

The journal encourages diversity and people from industry and/or government organisations who possess a strong track record in AI to apply.

Areas of particular interest include: Adversarial Learning, Bayesian Networks, Distributed Artificial Intelligence, Ethics of Artificial Intelligence, Fairness and Accountability of Artificial Intelligence, Human-AI Interaction / Teaming, Hyper and Meta Graphs, Knowledge-based Systems, Knowledge Graphs, Machine Learning for Image Processing, Machine Learning for Video Processing, Mathematical Logic, Multi-armed Bandit, Symbolic and non-Symbolic Knowledge Representation, Symbolic and non-Symbolic Natural Language Processing, Ontology, Probabilistic Reasoning, Reinforcement Learning, Sentiment Analysis, Swarm Robotics, Symbolic Reasoning, Trust in Artificial Intelligence, and Unmanned Systems.

Candidates interested in applying to join IEEE TAI’s editorial board must apply by filling the form here.

Live Webinar with Professor Anna Wilbik

Anna Wilbik is currently Professor in Data Fusion and Intelligent Interaction in the Department of Advanced Computing Sciences of Maastricht University, in the Netherlands. Currently she is also a chair of The Fuzzy Systems Technical Committee (FSTC) within IEEE CIS. 

Register

Comparing the Performance of Evolutionary Algorithms for Sparse Multi-Objective Optimization via a Comprehensive Indicator

Many real-world multi-objective optimization problems (MOPs) are characterized by a large number of decision variables, where the decision variables are mostly set to zero in the Pareto optimal solutions. Although some multi-objective evolutionary algorithms (MOEAs) have been tailored for large-scale MOPs in recent years, most of them do not consider the sparse nature of Pareto optimal solutions, and their effectiveness to sparse MOPs has not been investigated. Therefore, this work aims to compare the performance of MOEAs on sparse MOPs by suggesting a comprehensive performance indicator. Read More

IEEE Computational Intelligence Magazine, August 2022

Generating Black-Box Adversarial Examples in Sparse Domain

Applications of machine learning (ML) models and convolutional neural networks (CNNs) have been rapidly increased. Although state-of-the-art CNNs provide high accuracy in many applications, recent investigations show that such networks are highly vulnerable to adversarial attacks. The black-box adversarial attack is one type of attack that the attacker does not have any knowledge about the model or the training dataset, but it has some input data set and their labels. In this paper, we propose a novel approach to generate a black-box attack in sparse domain whereas the most important information of an image can be observed. Read More

Transactions on Emerging Topics in Computational Intelligence, August 2022

Constructing ANFIS With Sparse Data Through Group-Based Rule Interpolation: An Evolutionary Approach

An adaptive-network-based fuzzy inference system (ANFIS) offers a popular and powerful fuzzy inference mechanism. As with many other advanced data-driven techniques, developing an effective ANFIS typically requires sufficient training data. However, in many real-world applications, it is not always straightforward to obtain a large amount of representative data that cover the entire problem space to accomplish the required training, seriously restricting the performance of a learned ANFIS. This article introduces a new ANFIS learning approach through an evolutionary process, which is able to generate an ANFIS with only a small amount of training data in a certain problem region, by interpolating well-trained ANFISs in the neighboring regions.  Read more

IEEE Transactions on Fuzzy Systems, April 2022

A Gradient-Guided Evolutionary Approach to Training Deep Neural Networks

It has been widely recognized that the efficient training of neural networks (NNs) is crucial to classification performance. While a series of gradient-based approaches have been extensively developed, they are criticized for the ease of trapping into local optima and sensitivity to hyperparameters. Due to the high robustness and wide applicability, evolutionary algorithms (EAs) have been regarded as a promising alternative for training NNs in recent years. However, EAs suffer from the curse of dimensionality and are inefficient in training deep NNs (DNNs). By inheriting the advantages of both the gradient-based approaches and EAs, this article proposes a gradient-guided evolutionary approach to train DNNs. Read More

IEEE Transactions on Neural Networks and Learning Systems, September 2022

Region-Focused Memetic Algorithms With Smart Initialization for Real-World Large-Scale Waste Collection Problems

Memetic algorithm (MA) is widely applied to optimize routing problems as it provides one way to combine local search with global search. However, the local search in MA needs to be carefully designed according to the problem’s characteristics. In this article, we consider a real-world large-scale waste collection problem with multiple depots, multiple disposal facilities, multiple trips, and working time constraints. Vehicles with a limited capacity and working time can start from different depots, collect waste at different sites, and make multiple trips to different disposal facilities to empty the waste and return to its origin. While the existing work considered problems with multiple trips and time constraints, none have tackled problems with multiple depots, multiple disposal facilities, multiple trips, as well as working time constraints. Read More

IEEE Transactions on Evolutionary Computation, August 2022

Danesh: Interactive Tools for Understanding Procedural Content Generators

In order to advance the field of procedural content generation, and transfer knowledge from academic research to everyday use, we need to develop tools that make generative systems easier to understand and control. In this article, we introduce Danesh, a plugin to the unity game development environment, which helps provide a suite of tools that provide automation or analysis of different aspects of procedural generators. We describe here the features of Danesh, including automatic analysis of generated content, the visualization of generative spaces, automatic parameter discovery, and interface smoothing. We also provide reflections on our development of the tool so far. Read More

IEEE Transactions on Games, September 2022

Action Command Encoding for Surrogate-Assisted Neural Architecture Search

With the development of neural architecture search, the performance of deep neural networks has been considerably enhanced with less human expertise. While the existing work mainly focuses on the development of optimizers, the design of encoding scheme is still in its infancy. This article thus proposes a novel encoding scheme for neural architecture search, termed action command encoding (ACEncoding). Inspired by the gene expression process, ACEncoding defines several action commands to indicate the addition and clone of layers, connections, and local modules, where an architecture grows from empty according to multiple action commands. ACEncoding provides a compact and rich search space that can be explored by various optimizers efficiently. Read More

IEEE Transactions on Cognitive and Developmental Systems, August 2022

IEEE CIS Summer School 2022 at NIT Arunachal Pradesh

The main objective of the summer school is to understand the importance and relevance of emerging research trends in Computational Intelligence (CI) techniques among the community of young researchers and to acquire transversal skills in the wide range of biomedical data and imaging applications development. This summer school is not only offering the lectures but also providing a wonderful opportunity for young researchers and students to participate in interactive session for building their confidence and knowledge. Several well-known and renowned speakers of the relevant fields will exchange their learning, research ideas and hands-on training among the summer school participants that will be helpful in the future of research direction. The attractive feature of this summer school is to contribute knowledge by following the recent advancement of computational intelligence for biomedical imaging and data with different application domains.

Website: cis.nitap.ac.in

Dates: 7-11 November 2022

Venue: NIT Arunachal Pradesh, India Theme: Emerging Research Trends in Computational Intelligence Techniques to address Challenges in Biomedical Data and Imaging (hybrid mode).

Call for the 2022 Competition on Solar Generation Forecasting

Benchmarking of artificial intelligence methods for solar generation forecasting to address the increasing importance of energy resources forecasting in current and future power and energy systems.

Deadline: 31 October 2022

Organizers: Tiago Pinto, Zita Vale, and Luis Gomes (Polytechnic of Porto, Portugal) Supported by IEEE CIS Task Force on Computational Intelligence in the Energy Domain.

Competition Website: http://www.gecad.isep.ipp.pt/smartgridcompetition-forecast/

Scope and Topics: Energy resources forecasting is increasingly important in current and future power and energy systems. Due to the high uncertainty of generation based on renewable energy sources, which results from their dependence on weather conditions, such as wind speed or solar intensity, the need to develop suitable solutions to deal with such variability increases considerably. This competition fosters the benchmarking of artificial intelligence methods for solar generation forecasting.

Submission Instructions: The forecasts for each hour of the 7 days must be submitted in XLS format after submission, the teams with the best results will be requested to present their solution in a remote session with the jury.

• IEEE TNNLS Special Issue on Deep Learning for Intelligent Media Computing and Applications (30 October 2022)
• IEEE TCDS Special Issue on Movement Sciences in Cognitive Systems (6 January 2023)
  
• IEEE TCDS Special Issue on Advancing Machine Intelligence with Neuromorphic Computing (31 January 2023)
• IEEE TETCI Special Issue on Resource Sustainable Computational and Artificial Intelligence (1 February 2023)
• IEEE TNNLS Special Issue on Learning Theories and Methods with Application to Digitized Process Manufacturing (31 March 2023)